© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Joseph Bloom · Open Source Sparse Autoencoders for all Residual Stream Layers of GPT2-Small
    3. GPT2-Small
    4. Residual Stream
    5. 4-RES-JB
    6. 16069
    Prev
    Next
    INDEX
    Explanations

    text related to legal or procedural terms, such as "connection," "vendor," "litigation," and "trial."

    oai_token-act-pair · gpt-3.5-turbo

    connections and relationships between entities or concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GPT2-SMALL @ 4-res-jb
    Configuration
    jbloom/GPT2-Small-SAEs-Reformatted/blocks.4.hook_resid_pre
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Skylion007/openwebtext
    Features
    24,576
    Data Type
    torch.float32
    Hook Point
    blocks.4.hook_resid_pre
    Architecture
    standard
    Context Size
    128
    Dataset
    Skylion007/openwebtext
    Hook Point Layer
    4
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BuyableInstoreAndOnline
    -0.78
    izza
    -0.67
    gage
    -0.63
    Giving
    -0.61
    mx
    -0.60
    DNA
    -0.60
    anchester
    -0.60
    agos
    -0.59
    urst
    -0.58
    MSN
    -0.58
    POSITIVE LOGITS
     accordingly
    1.17
     alike
    1.03
     consequently
    1.02
     therein
    1.01
     thereafter
    1.00
    etheless
    0.95
     importantly
    0.95
     thereof
    0.91
     consequ
    0.90
     moreover
    0.89
    Activations Density 0.967%

    No Known Activations